-
Patent Agency Ranking
公开(公告)号：US12148197B2
公开(公告)日：2024-11-19
申请号：US17611517
申请日：2020-05-14
Applicant: BASF SE
Inventor： Artzai Picon Ruiz , Matthias Nachtmann , Maximilian Seitz , Patrick Mohnke , Ramon Navarra-Mestre , Alexander Johannes , Till Eggers , Amaia Maria Ortiz Barredo , Aitor Alvarez-Gila , Jone Echazarra Huguet
Abstract: A computer-implemented method, computer program product and computer system (100) for detecting plant diseases. The system stores a convolutional neural network (120) trained with a multi-crop dataset. The convolutional neural network (120) has an extended topology comprising an image branch (121) based on a classification convolutional neural network for classifying the input images according to plant disease specific features, a crop identification branch (122) for adding plant species information, and a branch integrator for integrating the plant species information with each input image. The plant species information (20) specifies the crop on the respective input image (10). The system receives a test input comprising an image (10) of a particular crop (1) showing one or more particular plant disease symptoms, and further receives a respective crop identifier (20) associated with the test input via an interface (110). A classifier module (130) of the system applies the trained convolutional network (120) to the received test input, and provides a classification result (CR1) according to the output vector of the convolutional neural network (120). The classification result (CR1) indicates the one or more plant diseases associated with the one or more particular plant disease symptoms.
-
公开(公告)号：US20210398190A1
公开(公告)日：2021-12-23
申请号：US17285235
申请日：2019-10-18
Applicant: BASF SE
Inventor： Klaus Stenzel , Maximilian Seitz , Matthias Nachtmann
Abstract: A system (100), method and computer program product for optimization of crop protection, for a particular crop in a particular field. The system receives a predetermined future time interval and real-time weather forecast data and can retrieve corresponding predicted target pressure data (122) representing expected biotic stress factor probabilities for said crop from a crop state prediction model. An optimizer (150) receives the predicted target pressure data (122) for one or more targets and determines an initial target pressure score for the particular field by aggregating all target pressure data in the predetermined future time interval. A protection product recommender (270) provides a plurality of product recommendations with each product recommendation including a mix of protection products suitable for treatment of the one or more targets, and each protection product having protection product characteristics (265) describing the treatment effect of the respective protection product by target. The optimizer determines further target pressure scores for a plurality of combinations of product recommendations and product application time slots by applying the respective protection product characteristics (265) to the target pressure data, and selects the combination with the target pressure score indicating the lowest expected biotic stress for the crop in the field as recommended combination.
-
公开(公告)号：US12086858B2
公开(公告)日：2024-09-10
申请号：US17285235
申请日：2019-10-18
Applicant: BASF SE
Inventor： Klaus Stenzel , Maximilian Seitz , Matthias Nachtmann
IPC: G06Q30/00 , A01B79/00 , G01W1/10 , G06Q10/04 , G06Q10/063 , G06Q30/0282 , G06Q30/0601 , G06Q50/02
CPC classification number: G06Q30/0631 , A01B79/005 , G01W1/10 , G06Q10/04 , G06Q10/063 , G06Q30/0282 , G06Q50/02
Abstract: A system (100), method and computer program product for optimization of crop protection, for a particular crop in a particular field. The system receives a predetermined future time interval and real-time weather forecast data and can retrieve corresponding predicted target pressure data (122) representing expected biotic stress factor probabilities for said crop from a crop state prediction model. An optimizer (150) receives the predicted target pressure data (122) for one or more targets and determines an initial target pressure score for the particular field by aggregating all target pressure data in the predetermined future time interval. A protection product recommender (270) provides a plurality of product recommendations with each product recommendation including a mix of protection products suitable for treatment of the one or more targets, and each protection product having protection product characteristics (265) describing the treatment effect of the respective protection product by target. The optimizer determines further target pressure scores for a plurality of combinations of product recommendations and product application time slots by applying the respective protection product characteristics (265) to the target pressure data, and selects the combination with the target pressure score indicating the lowest expected biotic stress for the crop in the field as recommended combination.
-
公开(公告)号：US11593897B2
公开(公告)日：2023-02-28
申请号：US16649696
申请日：2018-09-10
Applicant: BASF SE
Inventor： Klaus Stenzel , Maximilian Seitz , Matthias Nachtmann
Abstract: A system (100), method and computer program product for optimization of crop protection. A generator module (120) accesses one or more configuration data structures (220) wherein the one or more configuration data structures include data fields to store crop data (221), advice data (222) related to respective crop data, and crop protection product data (223) related to respective advice. Further, it accesses a plurality of code snippets (230) wherein each code snippet (231, 232, 233) has a condition which relates either to at least one property field of the one or more data structures (220) or to a result of another code snippet, and further includes generic program logic associated with the condition, and wherein each property field is used in the condition of at least one code snippet. The plurality of code snippets is applied to the one or more configuration data structures to generate an advice logic program.
-
公开(公告)号：US20200273117A1
公开(公告)日：2020-08-27
申请号：US16649696
申请日：2018-09-10
Applicant: BASF SE
Inventor： Klaus Stenzel , Maximilian Seitz , Matthias Nachtmann
Abstract: A system (100), method and computer program product for optimization of crop protection. A generator module (120) accesses one or more configuration data structures (220) wherein the one or more configuration data structures include data fields to store crop data (221), advice data (222) related to respective crop data, and crop protection product data (223) related to respective advice. Further, it accesses a plurality of code snippets (230) wherein each code snippet (231, 232, 233) has a condition which relates either to at least one property field of the one or more data structures (220) or to a result of another code snippet, and further includes generic program logic associated with the condition, and wherein each property field is used in the condition of at least one code snippet. The plurality of code snippets is applied to the one or more configuration data structures to generate an advice logic program. The system receives input (210) reflecting a real world field situation. A processor module (150) of the system to applies the generated advice logic program (130) to the received input (210) to generate a crop protection product mix instruction (140) applicable to the real world field situation.
-
-
-
-
Search Results
5
records
(took 0.013 seconds)
